StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909979765637120 |
|---|---|
| author | Mohanty, Shaswat |
| author_facet | Mohanty, Shaswat |
| contents | Accurate forecasting of financial markets remains a long-standing challenge due to complex temporal and often latent dependencies, non-linear dynamics, and high volatility. Building on our earlier recurrent neural network framework, we present an enhanced StockBot architecture that systematically evaluates modern attention-based, convolutional, and recurrent time-series forecasting models within a unified experimental setting. While attention-based and transformer-inspired models offer increased modeling flexibility, extensive empirical evaluation reveals that a carefully constructed vanilla LSTM consistently achieves superior predictive accuracy and more stable buy/sell decision-making when trained under a common set of default hyperparameters. These results highlight the robustness and data efficiency of recurrent sequence models for financial time-series forecasting, particularly in the absence of extensive hyperparameter tuning or the availability of sufficient data when discretized to single-day intervals. Additionally, these results underscore the importance of architectural inductive bias in data-limited market prediction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00197 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices Mohanty, Shaswat Computational Engineering, Finance, and Science Computation and Language Machine Learning Accurate forecasting of financial markets remains a long-standing challenge due to complex temporal and often latent dependencies, non-linear dynamics, and high volatility. Building on our earlier recurrent neural network framework, we present an enhanced StockBot architecture that systematically evaluates modern attention-based, convolutional, and recurrent time-series forecasting models within a unified experimental setting. While attention-based and transformer-inspired models offer increased modeling flexibility, extensive empirical evaluation reveals that a carefully constructed vanilla LSTM consistently achieves superior predictive accuracy and more stable buy/sell decision-making when trained under a common set of default hyperparameters. These results highlight the robustness and data efficiency of recurrent sequence models for financial time-series forecasting, particularly in the absence of extensive hyperparameter tuning or the availability of sufficient data when discretized to single-day intervals. Additionally, these results underscore the importance of architectural inductive bias in data-limited market prediction tasks. |
| title | StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices |
| topic | Computational Engineering, Finance, and Science Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2601.00197 |